{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HH2XBH4CUUO4TYM3T55EJBFESW","short_pith_number":"pith:HH2XBH4C","schema_version":"1.0","canonical_sha256":"39f5709f82a51dc9e19b9f7a4484a4959a2d33e0c7ed0619093983ee2f049c03","source":{"kind":"arxiv","id":"2306.05076","version":1},"attestation_state":"computed","paper":{"title":"DLAMA: A Framework for Curating Culturally Diverse Facts for Probing the Knowledge of Pretrained Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amr Keleg, Walid Magdy","submitted_at":"2023-06-08T09:59:48Z","abstract_excerpt":"A few benchmarking datasets have been released to evaluate the factual knowledge of pretrained language models. These benchmarks (e.g., LAMA, and ParaRel) are mainly developed in English and later are translated to form new multilingual versions (e.g., mLAMA, and mParaRel). Results on these multilingual benchmarks suggest that using English prompts to recall the facts from multilingual models usually yields significantly better and more consistent performance than using non-English prompts. Our analysis shows that mLAMA is biased toward facts from Western countries, which might affect the fair"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2306.05076","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-08T09:59:48Z","cross_cats_sorted":[],"title_canon_sha256":"b14de17a985a4f5c8b94e6184b58eb545f9c348cc23886e4462938421bdfb7ad","abstract_canon_sha256":"b0b07d3d497213599fbdc030202f722d0cfdae626f7e3920282f03916c302494"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:45.492569Z","signature_b64":"hWbMaX7g1liqTmc3kqvM4My+TjFymRQOqIHZyF/SYz3yU26rSUCMNhZzcg//hjuUFSYMgzRSkKC9vdpZZwACBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39f5709f82a51dc9e19b9f7a4484a4959a2d33e0c7ed0619093983ee2f049c03","last_reissued_at":"2026-07-05T06:18:45.492056Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:45.492056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DLAMA: A Framework for Curating Culturally Diverse Facts for Probing the Knowledge of Pretrained Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amr Keleg, Walid Magdy","submitted_at":"2023-06-08T09:59:48Z","abstract_excerpt":"A few benchmarking datasets have been released to evaluate the factual knowledge of pretrained language models. These benchmarks (e.g., LAMA, and ParaRel) are mainly developed in English and later are translated to form new multilingual versions (e.g., mLAMA, and mParaRel). Results on these multilingual benchmarks suggest that using English prompts to recall the facts from multilingual models usually yields significantly better and more consistent performance than using non-English prompts. Our analysis shows that mLAMA is biased toward facts from Western countries, which might affect the fair"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05076","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2306.05076/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2306.05076","created_at":"2026-07-05T06:18:45.492115+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.05076v1","created_at":"2026-07-05T06:18:45.492115+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05076","created_at":"2026-07-05T06:18:45.492115+00:00"},{"alias_kind":"pith_short_12","alias_value":"HH2XBH4CUUO4","created_at":"2026-07-05T06:18:45.492115+00:00"},{"alias_kind":"pith_short_16","alias_value":"HH2XBH4CUUO4TYM3","created_at":"2026-07-05T06:18:45.492115+00:00"},{"alias_kind":"pith_short_8","alias_value":"HH2XBH4C","created_at":"2026-07-05T06:18:45.492115+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2401.00761","citing_title":"Identifying the Achilles' Heel: An Iterative Method for Dynamically Uncovering Factual Errors in Large Language Models","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2412.20760","citing_title":"Attributing Culture-Conditioned Generations to Pretraining Corpora","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HH2XBH4CUUO4TYM3T55EJBFESW","json":"https://pith.science/pith/HH2XBH4CUUO4TYM3T55EJBFESW.json","graph_json":"https://pith.science/api/pith-number/HH2XBH4CUUO4TYM3T55EJBFESW/graph.json","events_json":"https://pith.science/api/pith-number/HH2XBH4CUUO4TYM3T55EJBFESW/events.json","paper":"https://pith.science/paper/HH2XBH4C"},"agent_actions":{"view_html":"https://pith.science/pith/HH2XBH4CUUO4TYM3T55EJBFESW","download_json":"https://pith.science/pith/HH2XBH4CUUO4TYM3T55EJBFESW.json","view_paper":"https://pith.science/paper/HH2XBH4C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.05076&json=true","fetch_graph":"https://pith.science/api/pith-number/HH2XBH4CUUO4TYM3T55EJBFESW/graph.json","fetch_events":"https://pith.science/api/pith-number/HH2XBH4CUUO4TYM3T55EJBFESW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HH2XBH4CUUO4TYM3T55EJBFESW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HH2XBH4CUUO4TYM3T55EJBFESW/action/storage_attestation","attest_author":"https://pith.science/pith/HH2XBH4CUUO4TYM3T55EJBFESW/action/author_attestation","sign_citation":"https://pith.science/pith/HH2XBH4CUUO4TYM3T55EJBFESW/action/citation_signature","submit_replication":"https://pith.science/pith/HH2XBH4CUUO4TYM3T55EJBFESW/action/replication_record"}},"created_at":"2026-07-05T06:18:45.492115+00:00","updated_at":"2026-07-05T06:18:45.492115+00:00"}